Steven Li
Community@yo-steven
2nd biggest fan of Garry Tan
Agent Skills by Steven Li
Showing 158 vetted skills indexed across 4 GitHub repositories.
yo-stevenseedance-podcast-visual
Generate Seedance 2.0 video prompts from podcast audio clips.
yo-stevenseedance-before-after
Generate Seedance 2.0 transformation reveal video prompts with user-defined parameters.
yo-stevenseedance-ai-avatar
Generate AI avatar visuals and video prompts for Seedance AI.
yo-stevenseedance-personal-brand
Create personalized video prompts for personal brand authority content.
yo-stevenseedance-testimonial-story
Generate video prompts for customer testimonial stories with input templates and output specifications.
yo-stevenseedance-luxury-aesthetic
Generate luxury aesthetic video prompts for Seedance 2.0.
yo-stevenseedance-saas-launch
Generate structured video prompts for SaaS product launches and software demos.
yo-stevenseedance-viral-hook
Generates short-form video prompts for Seedance 2.0 using images, videos, audio, and text.
yo-stevenseedance-course-promo
Construct cinematic video prompts for educational content on Seedance 2.0.
yo-stevenseedance-faceless-channel
Generate faceless video prompts for YouTube, TikTok, and Reels.
yo-stevenai-text-detector-github
Detect AI-like text and output risk estimates with confidence levels.
yo-stevenai-detector
Analyze text for AI-generated likelihood using predefined rules and signals.
yo-steven1688-shopkeeper
Automate 1688 shopkeeper sourcing, binding, and publishing across multiple channels.
yo-stevennemotron-voice-agent-deploy
Deploy real-time speech-to-speech voice agents using NVIDIA ASR, TTS, and LLM components.
yo-stevenmonitor
Monitor SLURM and NVIDIA jobs, reporting state changes every 15 minutes.
yo-stevenptq
Quantize pretrained LLMs and VLMs into HuggingFace or TensorRT-LLM checkpoints.
yo-stevenlaunching-evals
Run, monitor, and debug LLM evaluation jobs on Slurm with nemo-evaluator-launcher.
yo-stevendeployment
Deploy HF LLM checkpoints as OpenAI-compatible endpoints via vLLM, SGLang, or TRT-LLM.
yo-stevenevaluation
Generate NEL configurations and execute LLM accuracy benchmarks on local or SLURM backends.
yo-stevenaccessing-mlflow
Query MLflow evaluation results by invocation_id and tags to extract artifacts.
yo-stevenrelease-cherry-pick
Cherry-pick labeled merged pull requests from main onto release branches.
yo-stevendebug
Execute diagnostic and test commands inside a Docker container via a file-based relay.
yo-stevennemo-gym-docs
Maintain NeMo Gym Fern MDX documentation pages and navigation.
yo-stevennemo-gym-reward-profiling
Join materialized inputs with rollout results for Nemo Gym reward profiling.